System and method for predicting user traffic trends for resource allocation management in communication networks

Abstract

Disclosed is a system and a method for predicting user traffic trends for resource allocation management in a communication network (100). The method comprises collecting network data from a plurality of serving cells (110) serving a plurality of User Equipment (UEs) (120). Using a computational model (308-3), a trend in a user traffic served by a set of serving cells among the plurality of serving cells (110) during a pre-defined time-period is predicted based on the collected network data. Based on the predicted trend in the user traffic, one or more serving cells in the set of serving cells are identified for adjusting parameters corresponding to one or more resources of the one or more serving cells. Based on the predicted trend in the user traffic and the identified one or more serving cells, visualization data is generated and parameters corresponding to one or more resources are adjusted.

Description

SYSTEM AND METHOD FOR PREDICTING USER TRAFFIC TRENDS FOR RESOURCE ALLOCATION MANAGEMENT IN COMMUNICATION NETWORKSTECHNICAL FIELD

[0001] The embodiments of the present disclosure generally relate to the field of wireless communication networks. More particularly, the present disclosure relates to a system and method for predicting user traffic trends for resource allocation management in the communication networks.BACKGROUND OF THE INVENTION

[0002] The subject matter disclosed in the background section should not be assumed or construed to be prior art merely as a result of its mention in the background section. Similarly, any problem statement mentioned in the background section or its association with the subject matter of the background section should not be assumed or construed to have been previously recognized in the prior art.

[0003] With growth of wireless communication networks around the world, network operators are striving to increase robustness of the communication network that is capable of supporting a plurality of user devices on the communication network. To consistently improve overall services of the communication network in an entire coverage area, the network operators strive to prevent network congestion and maintain a level of Quality of Service (QoS) in the communication network.

[0004] Conventionally, the network operators rely on estimating periods of high network usage, such as peak hours during a day or during extraordinary events. Based on the estimations, the network operators adjust network resources such as bandwidth allocation and servers in advance to minimize issues like call drops, slow internet speeds, and buffering during peak usage times. However, there are limitations attached to the conventional techniques that the estimations of user traffic are not accurate as they rely on static parameters for estimating the periodsof high network usage and fail to take into account a dynamic volatility in the communication network. As a result, the conventional techniques lead to latency and scalability issues in the communication network.

[0005] Therefore, there lies a need for an improved system and method to overcome the aforementioned problems associated with the conventional techniques for management of network resource allocation in the communication network.SUMMARY

[0006] The following embodiments present a simplified summary in order to provide a basic understanding of some aspects of the disclosed invention. This summary is not an extensive overview, and it is not intended to identify key / critical elements or to delineate the scope thereof. Its sole purpose is to present some concepts in a simplified form as a prelude to the more detailed description that is presented later.

[0007] In an embodiment, disclosed herein is a method for predicting user traffic trends for resource allocation management in a communication network. The method comprises collecting, by an acquisition module, network data from a plurality of serving cells serving a plurality of User Equipment (UEs) in the communication network. The method further comprises predicting, by a data computation module using a computational model, a trend in a user traffic served by a set of serving cells among the plurality of serving cells during a pre-defined time-period based on the collected network data. Further, the method comprises identifying, by the data computation module based on the predicted trend in the user traffic, one or more serving cells in the set of serving cells for adjusting parameters corresponding to one or more resources of the one or more serving cells. Furthermore, the method comprises generating, by a processing module based on the predicted trend in the user traffic and the identified one or more serving cells, visualization data including information related to the one or more resources of the one or more serving cells during the pre-defined time-period. Thereafter, the methodcomprises adjusting, by the processing module, the parameters corresponding to the one or more resources based on the generated visualization data.

[0008] In one aspect, for predicting the trend, the method further comprises aggregating, by the data computation module from the network data, a first set of Key Performance Indicators (KPIs) related to the plurality of UEs and a second set of KPIs related to the plurality of serving cells at a plurality of timestamps of a predefined rolling time window among a plurality of pre-defined rolling time windows. Further, the method comprises determining, by the data computation module, an average value of each KPI in each of the first set of KPIs and the second set of KPIs at each timestamp of the plurality of timestamps of the pre-defined rolling time window. The method further comprises comparing, by the data computation module, the determined average value of each KPI with one or more pre-defined threshold ranges of the first set of KPIs and the second set of KPIs. Further, the method comprises identifying, by the data computation module based on the comparison, a pre-defined threshold range among the one or more pre-defined threshold ranges that includes the determined average value of each KPI.

[0009] In one aspect, for predicting the trend, the method further comprises determining, by the data computation module using the computational model based on the identified pre-defined threshold range, a deviation in the average value of each KPI when the average value falls outside the identified pre-defined threshold range in a subsequent rolling time window of the plurality of pre-defined rolling time windows. Further, the method comprises identifying, by the data computation module using the computational model, a historical pattern of the user traffic at each serving cell of the plurality of serving cells during the pre-defined rolling time window based on the determined deviation. The method further comprises predicting, by the data computation module using the computational model, the trend in the user traffic of the set of serving cells among the plurality of serving cells during the pre-defined rolling time window based on the identified historical pattern of the user traffic.

[0010] In one aspect, for predicting the trend, the method further comprises, determining, by the data computation module using the collected network data, a traffic behavior profile of a UE of the plurality of UEs based on one or more a type of service availed by the UE from the communication network, a time of availing the service, a device type of the UE that has availed the service.

[0011] In one aspect, the network data includes information related to at least one of a number of active UEs among the plurality of UEs served by a serving cell of the plurality of serving cells during the pre-defined time-period, a total number of UEs among the plurality of UEs attached to the serving cell during the pre-defined time-period, historical network usage data associated with a UE of the plurality of UEs during the pre-defined time-period, a type of service availed by the UE from the communication network, a time of availing the service, a type of the UE availing the services, and one or more of a first set of Key Performance Indicators (KPIs) related to the plurality of UEs and a second set of KPIs related to the plurality of serving cells.

[0012] In one aspect, the method further comprises sending, by a transceiver module, the generated visualization data to a network management device for displaying the generated visualization data for the adjustment of the parameters corresponding to the one or more resources. The generated visualization data comprises a performance metric report including information indicative of performance of the set of serving cells serving the plurality of UEs.

[0013] According to another aspect of the present disclosure, disclosed is a system for predicting user traffic trends for resource allocation management in a communication network. The system comprises an acquisition module, a data computation module, and a processing module. The acquisition module is configured to collect network data from a plurality of serving cells serving a plurality of User Equipment (UEs) in the communication network. The data computation module is configured to predict, using a computational model, a trend in a user traffic served by a set of serving cells among the plurality of serving cellsduring a pre-defined time-period based on the collected network data. Further, the data computation module is configured to identify, based on the predicted trend in the user traffic, one or more serving cells in the set of serving cells for adjusting parameters corresponding to one or more resources of the one or more serving cells. The processing module is configured to generate, based on the predicted trend in the user traffic and the identified one or more serving cells, visualization data including information related to the one or more resources of the one or more serving cells during the pre-defined time-period. Further, the processing module is configured to adjust the parameters corresponding to the one or more resources based on the generated visualization data.

[0014] In one aspect, the data computation module is further configured to aggregate, from the network data, a first set of Key Performance Indicators (KPIs) related to the plurality of UEs and a second set of KPIs related to the plurality of serving cells at a plurality of timestamps of a pre-defined rolling time window among a plurality of pre-defined rolling time windows. Further, the data computation module is configured to determine an average value of each KPI in each of the first set of KPIs and the second set of KPIs at each timestamp of the plurality of timestamps of the pre-defined rolling time window. The data computation module is further configured to compare the determined average value of each KPI with one or more pre-defined threshold ranges of the first set of KPIs and the second set of KPIs and identify, based on the comparison, a pre-defined threshold range among the one or more pre-defined threshold ranges that includes determined the average value of each KPI.

[0015] In one aspect, for predicting the trend, the data computation module is configured to determine, using the computational model based on the identified predefined threshold range, a deviation in the average value of each KPI when the average value falls outside the identified pre-defined threshold range in a subsequent rolling time window of the plurality of pre-defined rolling time windows. Further, the data computation module is configured to identify, using the computational model, a historical pattern of the user traffic at each serving cell of the plurality ofserving cells during the pre-defined rolling time window based on the determined deviation and predict, using the computational model, the trend in the user traffic of the set of serving cells among the plurality of serving cells during the pre-defined rolling time window based on the identified historical pattern of the user traffic.

[0016] In one aspect, for predicting the trend, the data computation module is further configured to determine, using the collected network data, a traffic behavior profile of a UE of the plurality of UEs based on one or more a type of service availed by the UE from the communication network, a time of availing the service, a device type of the UE that has availed the service.

[0017] In one aspect, the network data includes information related to at least one of a number of active UEs among the plurality of UEs served by a serving cell of the plurality of serving cells during the pre-defined time-period, a total number of UEs among the plurality of UEs attached to the serving cell during the pre-defined time-period, historical network usage data associated with a UE of the plurality of UEs during the pre-defined time-period, a type of service availed by the UE from the communication network, a time of availing the service, a type of the UE availing the services, and one or more of a first set of Key Performance Indicators (KPIs) related to the plurality of UEs and a second set of KPIs related to the plurality of serving cells.

[0018] In one aspect, the system further comprises a transceiver module configured to send the generated visualization data to a network management device for displaying the generated visualization data for the adjustment of the parameters corresponding to the one or more resources. The generated visualization data comprises a performance metric report including information indicative of performance of the set of serving cells serving the plurality of UEs.BREIF DESCRIPTION OF DRAWINGS

[0019] Various embodiments disclosed herein will become better understood from the following detailed description when read with the accompanying drawings. Theaccompanying drawings constitute a part of the present disclosure and illustrate certain non-limiting embodiments of inventive concepts. Further, components and elements shown in the drawings are not necessarily to scale, emphasis instead being placed upon clearly illustrating the principles of the present disclosure. For the purpose of consistency and ease of understanding, similar components and elements are annotated by reference numerals in the exemplary drawings.

[0020] FIG. 1 illustrates a block diagram depicting an exemplary environment of a communication network, in accordance with an embodiment of the present disclosure.

[0021] FIG. 2 illustrates a block diagram depicting a system for predicting user traffic trends for resource allocation management in the communication network, in accordance with an embodiment of the present disclosure.

[0022] FIG. 3 illustrates a block diagram depicting an architecture of a server, in accordance with an embodiment of the present disclosure.

[0023] FIG. 4 illustrates a flow chart of a method for predicting user traffic trends for resource allocation management in the communication network, in accordance with an embodiment of the present disclosure.DETAILED DESCRIPTION OF THE INVENTION

[0024] Inventive concepts of the present disclosure will now be described more fully hereinafter with reference to the accompanying drawings, in which examples of one or more embodiments of inventive concepts are shown. Inventive concepts may, however, be embodied in different forms and should not be construed as limited to the embodiments set forth herein. Further, the one or more embodiments disclosed herein are provided to describe the inventive concept thoroughly and completely, and to fully convey the scope of each of the present inventive concepts to those skilled in the art. Furthermore, it should be noted that the embodiments disclosed herein are not mutually exclusive concepts. Accordingly, one or morecomponents from one embodiment may be tacitly assumed to be present or used in any other embodiment.

[0025] The following description presents various embodiments of the present disclosure. The embodiments disclosed herein are presented as teaching examples and are not to be construed as limiting the scope of the present disclosure. The present disclosure should in no way be limited to the illustrative implementations, drawings, and techniques illustrated below, including the exemplary design and implementation illustrated and described herein, but may be modified, omitted, or expanded upon without departing from the scope of the present disclosure.

[0026] The following description contains specific information pertaining to embodiments in the present disclosure. The detailed description uses the phrases “in some embodiments” which may each refer to one or more or all of the same or different embodiments. The term “some” as used herein is defined as “one, or more than one, or all.” Accordingly, the terms “one,” “more than one,” “more than one, but not all” or “all” would all fall under the definition of “some.” In view of the same, the terms, for example, “in an embodiment” refers to one embodiment and the term, for example, “in one or more embodiments” refers to “at least one embodiment, or more than one embodiment, or all embodiments.”

[0027] The term “comprising,” when utilized, means “including, but not necessarily limited to;” it specifically indicates open-ended inclusion in the so-described one or more listed features, elements in a combination, unless otherwise stated with limiting language. Furthermore, to the extent that the terms “includes,” “has,” “have,” “contains,” and other similar words are used in either the detailed description, such terms are intended to be inclusive in a manner similar to the term “comprising.”

[0028] In the following description, for the purposes of explanation, various specific details are set forth in order to provide a thorough understanding of embodiments of the present disclosure. It will be apparent, however, that embodiments of the present disclosure may be practiced without these specificdetails. Several features described hereafter can each be used independently of one another or with any combination of other features.

[0029] The description provided herein discloses exemplary embodiments only and is not intended to limit the scope, applicability, or configuration of the present disclosure. Rather, the foregoing description of the exemplary embodiments will provide those skilled in the art with an enabling description for implementing any of the exemplary embodiments. Specific details are given in the following description to provide a thorough understanding of the embodiments. However, it may be understood by one of the ordinary skilled in the art that the embodiments disclosed herein may be practiced without these specific details.

[0030] The terminology used herein is for the purpose of describing particular embodiments only and is not intended to be limiting of the disclosure. As used herein the description, the singular forms "a", "an", and "the" include plural forms unless the context of the invention indicates otherwise.

[0031] The terminology and structure employed herein are for describing, teaching, and illuminating some embodiments and their specific features and elements and do not limit, restrict, or reduce the scope of the present disclosure. Accordingly, unless otherwise defined, all terms, and especially any technical and / or scientific terms, used herein may be taken to have the same meaning as commonly understood by one having ordinary skill in the art.

[0032] In the disclosure, various embodiments are described using terms used in some communication standards (e.g., 3rd Generation Partnership Project (3GPP), xRadio Access Network (xRAN), and Open-Radio Access Network (0-RAN)), but these are merely examples for description. Various embodiments of the disclosure may also be easily modified and applied to other communication systems.

[0033] In order to facilitate an understanding of the disclosed invention, a number of terms are defined below.

[0034] Reference Signal Received Power (RSRP) may refer to an average power level of reference signals received from a specific serving cell, measured in dBm. The RSRP provides an indication of the signal strength and may be used to evaluate coverage quality.

[0035] Reference Signal Received Quality (RSRQ) may refer to a measure of the quality of the received reference signal, calculated as a ratio of the RSRP to total received power.

[0036] Signal-to-Interference-plus-Noise Ratio (SINR) may represent a ratio of a power of a useful signal to a power of interference plus background noise, typically expressed in decibels (dB). The SINR may determine a signal quality experienced by the UE.

[0037] An object of the present disclosure is to provide a system and a method for predicting user traffic trends for resource allocation management in the communication networks. Another object of the present disclosure is to implement pre-emptive resource allocation in the communication network based on the predicted user traffic trends to improve user experience. Still another object of the present disclosure is to provide a system and method that can pre-empt sudden spikes or shifts in user demand in a specific time period. Yet another object of the present disclosure is to provide a system and method that can offer flexibility to the network operators while managing sudden the spikes or shifts in the user demand without compromising a quality of service in the communication network.

[0038] Embodiments of the present disclosure will be described below in detail with reference to the accompanying drawings. FIG. 1 through FIG. 4, discussed below, and the one or more embodiments used to describe the principles of the present disclosure are by way of illustration only and should not be construed in any way to limit the scope of the present disclosure. Those skilled in the art will understand that the principles of the present disclosure may be implemented in any suitably arranged system or device.

[0039] FIG. 1 illustrates a block diagram depicting an exemplary environment of a communication network 100, in accordance with an embodiment of the present disclosure. The embodiment of the communication network 100 shown in FIG. 1 is for illustration only. Other embodiments of the communication network 100 may be used without departing from the scope of this disclosure. The communication network 100 may comprise one or more nodes 110-1 through 110-n (cumulatively referred to as “nodes 110” and alternatively referred to as “plurality of serving cells 110” or “serving cells 110”) connected to a plurality of User Equipment (UEs) 120- 1 through 120-n (cumulatively referred to as “UEs 120”) through a network 130. The nodes 110 and the UEs 120 are also communicably connected to a server 140.

[0040] The term “node 110” may refer to any component (or collection of components) configured to provide wireless access to a network. The BS may be a network infrastructure that provides wireless access to one or more terminals. The base station provides coverage to a plurality of predetermined geographic areas based on distance over which a signal may be transmitted. Examples of the BS include, but are not limited to, the macro cell, the femtocell, small cells, micro cells, wireless “Access Point (AP),” “evolved NodeB (eNodeB) (eNB),” “5th Generation (5G) node,” “next generation NodeB (gNB),” “wireless point,” “Transmission / Reception Point (TRP) .” The BS may provide wireless access in accordance with wireless communication protocols, e.g., 5G / NR 3GPP New Radio interface / access (NR), LTE, LTE-A, High Speed Packet Access (HSPA), Wi-Fi 802.11a / b / g / n / ac, etc. The nodes 110 in the communication network 100 may be from same or different vendors having similar or different specification. Aspects of the present disclosure are intended to include, or otherwise cover, any technology (known or later developed) bearing same or similar characteristics as of the above- mentioned BS, without deviating from the scope of the present disclosure. For the sake of convenience, the terms “nodes” and “serving cells” are used interchangeably in the present disclosure to refer to network infrastructure components that provide wireless access to remote terminals.

[0041] Typically, the term “UE” can refer to any component such as “mobile station,” “subscriber station,” “remote terminal,” “wireless terminal,” “receive point,” or “end user device.” The UE 120 may correspond to, but is not limited to, any of mobile devices, tablets, or other portable devices utilized by users to access services provided by the communication network 100. The UEs 120 may be served by one or more of the plurality of nodes 110.

[0042] The UEs 120 may communicate with the serving cells 110 to avail services of the serving cells 110 through the network 130. The network 130 may include wired connections, wireless connections such as a proprietary Internet Protocol (IP) network, Internet, or in accordance with other wireless communication standards such as Worldwide Interoperability for Microwave Access (WiMAX), Wi-Fi 802.11a / b / g / n / ac, or a combination of wired and wireless connections.

[0043] At any point of time, one or more UEs of the UEs 120 may be attached to the serving cells 110 through a session to avail one or more communication services of the serving cells 110. During the session, the one or more UEs is configured to capture the network data including a first set of Key Performance Indicators (KPIs) related to the plurality of UEs 120. The first set of KPIs may include, but not limited to, one or more of Downlink (DL) speed, Uplink (UL) speed, network throughput, latency, jitter, RSRQ, RSRP, SINR, and call drop rate. The first set of KPIs may refer to quantifiable measures that reflect a quality of service received by the UEs 120.

[0044] During the session, the serving cells 110 are also configured to capture network data including a second set of KPIs related to the plurality of serving cells 110. The second set of KPIs may refer to quantifiable measures that reflect a behavioral state of the serving cells 110. The second set of KPIs may include, but not limited to, one or more of information related to a number of active UEs among the plurality of UEs 120 served by a serving cell of the plurality of serving cells 110 during the pre-defined time-period (alternatively referred to as “active user count”), a total number of UEs among the plurality of UEs 120 attached to the serving cellduring the pre-defined time-period (alternatively referred to as “attached user count”), and information corresponding to network usage data associated with services availed by each of the plurality of UEs 120 during the session with the plurality of serving cells 110. The active user count attached to the serving cell 110 indicates user traffic served by the serving cell 110 during the pre-defined timeperiod.

[0045] The network data obtained from one or more of the serving cells 110 and the UEs 120 further includes historical network usage data associated with each of the plurality of UEs 120 during the pre-defined time-period, subscriber behavior data, geographical data including geographical location of the plurality of UEs 120 served by the serving cells 110, subscriber activity corresponding to any particular site of the serving cells 110, a type of service availed by the UE of the plurality of UEs 120 from the communication network, a time of availing the service, a type of the UE of the plurality of UEs 120 availing the services, and real-time data such as metadata of the communication network 100 during the session of the plurality of the UEs 120 with the plurality of serving cells 110.

[0046] The server 140 obtains the network data periodically or on demand from one or more of the serving cells 110 and the UEs 120 directly or via a data collecting entity, for predicting user traffic trends for the resource allocation management. The server 140 may be a physical machine or a virtual machine in a cloud environment, a network of computers, a software framework, or a combination thereof, that may provide a generalized approach to create a server implementation. Examples of the server 140 may include, but are not limited to, personal computers, laptops, minicomputers, mainframe computers, any non-transient and tangible machine that can execute a machine-readable code, cloud-based servers, distributed server networks, or a network of computer systems. The server 140 may be controlled by a processor to perform one or more operations.

[0047] Although FIG. 1 illustrates one example of the communication network 100, various changes may be made to FIG. 1. Further, the communication network 100may include any number of components in addition to the components shown in FIG. 1. For example, the communication network environment may include any number of serving cells 110 and any number of UEs 120 in any suitable arrangement. Further, the serving cells 110 may communicate directly with any number of UEs and provide the UEs with wireless broadband access to the network 130. Each of the serving cells 110 may also communicate directly with the server 140. The serving cells 110 may provide access to other or additional external networks, such as external telephone networks or other types of data networks. Further, various components in FIG. 1 may be combined, further subdivided, or omitted and additional components may be added according to particular needs.

[0048] FIG. 2 illustrates a block diagram depicting a system 200 for predicting user traffic trends for resource allocation management in the communication networks, in accordance with an embodiment of the present disclosure. The embodiments of the system 200 shown in FIG. 2 are for illustration only. Other embodiments of the system 200 may be used without departing from the scope of this disclosure.

[0049] As shown in FIG. 2, the system 200 includes the server 140, a Network Management Console (NMC) 210 (alternatively referred to as “network management device 210”), a data collection entity 220, and a storage medium 230. The server 140 communicates with the NMC 210, the data collection entity 220, and the storage medium 230 via the network 130.

[0050] The data collection entity 220 is configured to collect the network data periodically, on demand, after an event or in real-time, from one or more of the serving cells 110 and the UEs 120. The data collection entity 220 is further configured to monitor the network data in real time during Bouncing Busy Hour (BBH) and Network Busy Hour (NBH) at the serving cells 110.

[0051] In one embodiment, the data collection entity 220 may be a server or a group of servers configured to collect and store the data. The group of servers may be one or more of a cloud-based server, an application server, a content server, a host server, a web server, a database server, or a server hosted over a desktop computer. Thegroup of servers may be hosted locally or over a cloud network. In another embodiment, the data collection entity 220 may be a database configured to store the data and communicate with the server 140.

[0052] Further, the data collection entity 220 sends the collected network data periodically or on demand to the server 140. The server 140 is further connected to the storage medium 230 for storing records of the network data received from the data collection entity 220. The storage medium 230 may generally be one or more of, without limitation, disk drives, hard-disk arrays, solid state storage devices, Network Attached Storage (NAS) devices, tape libraries or other magnetic, non-tape storage devices, and optical media storage devices. In one embodiment, the storage medium may form part of a Distributed File System (DFS). The DFS is configured to provide a scalable and fault-tolerant storage system, capable of handling entire operation specific data across distributed clusters of files associated with the server 140. In another embodiment, the storage medium may form part of a centralized database. The storage medium 230 may allow the server 140 seamless data access and retrieval as needed for processing and storage. In other embodiments, the storage medium 230 may be integrated within the server 140 for storing records of the network data.

[0053] The server 140 processes the network data through a computational model to predict user traffic trends for resource allocation management in the communication network 100. For an example, the computational model may predict that on weekends in the evenings or a festive holiday, the user traffic trend will rise in a specific geographical area. The computational model may include, but is not limited to, a Machine Learning (ML) model, an Artificial Intelligence (Al) model, an algorithmic model, a rule-based model, and a neural network. In one embodiment, the computational model based on statistical algorithms may be used. In one embodiment, the computational model may correspond to the ML model and henceforth be alternatively referred to as ML model. It must be understood that although usage of the ML model is merely described as an example, it is possible to utilize other computational models.

[0054] Based on the output data of the ML model, the server 140 generates visualization data including information related to the one or more resources of the one or more serving cells during the pre-defined time-period and predicted user traffic trends related to the one or more serving cells. The generated visualization data may also correspond to a performance metric report including information indicative of performance of the one or more serving cells serving the plurality of UEs 120.

[0055] Furthermore, the visualization data is sent by the server 140 to the NMC 210 for displaying the generated visualization data for the adjustment of the parameters corresponding to the one or more resources. The NMC 210 may be any client device or an electronic device such as “user device”, “User Equipment (UE)”, “mobile station,” “subscriber station,” “remote terminal,” “wireless terminal,” or “receive point”, a desktop computer, a portable computing devices such as laptops, tablet computers, handheld computer, mobile phones, wearable computers, or any other device suitable to provide front end services. The front-end services may include a Graphical User Interface (GUI) 212 (alternatively referred to as User Interface (UI) 212) for accessing different functionalities of the system 200. The GUI 212 may include a software or a web application for initiating user requests to the server 140 for predicting the user traffic trends in the communication network 100.

[0056] The server 140 controls the GUI 212 to present options to the network operator for specifying one or more of a pre-defined time-period and a geographical location of interest for set of serving cells among the plurality of serving cells 110 for resource allocation management. The server 140 further controls the GUI 212 to display the visualization data in a graphical format or pictorial format. The visualization data may be accessed by network operators on the NMC 210 in the form of the performance metric report for further assessment and taking further remedial actions for optimization of parameters corresponding to the one or more resources in the communication network 100.

[0057] The NMC 210 further comprises a communication unit 214 for communicating with the server 140. The communication unit 214 may include a plurality of antennas, a plurality of Radio Frequency (RF) transceivers, a transmit processing circuitry, and a receive processing circuitry. The communication unit 214 may also allow the NMC 210 to receive from the server 140, the visualization data corresponding to the predicted user traffic trends related to the set of serving cells.

[0058] Although FIG. 2 illustrates one example of the system 200, various changes may be made to FIG. 2. Further, the system 200 may include any number of components in addition to the components shown in FIG. 2. Further, various components in FIG. 2 may be combined, further subdivided, or omitted and additional components may be added according to particular needs, for example the data collection entity 220 and the storage medium 230 may be a single entity.

[0059] FIG. 3 illustrates a block diagram depicting an architecture of the server 140, in accordance with an embodiment of the present disclosure. The server 140 may include various hardware and software components such as an Input-Output (VO) interface 302, a network communication manager 304, a processor 306, a memory 308, a database 310, a communication interface 312, and a plurality of modules / units 314 (collectively referred to as the modules 314), network devices, and other drivers (not shown in FIG. 3). Components of the server 140 are coupled to each other via a communication bus 316.

[0060] The I / O interface 302 may include suitable logic, circuitry, interfaces, and / or codes that may be configured to receive input(s) and present (or display) output(s) on the server 140. For example, the I / O interface 302 may have an input interface and an output interface. The input interface may be configured to enable a user to provide input(s) to trigger (or configure) the server 140 to perform various operations for resource allocation management in the communication network 100, such as but not limited to, receiving the network data from the data collection entity 220. Examples of the input interface may include, but are not limited to, a touch interface, a mouse, a keyboard, and the output interface includes a digital display,an analog display, or a touch screen display. Aspects of the present disclosure are intended to include or otherwise cover any type of the input interface including known, related art, and / or later developed technologies without deviating from the scope of the present disclosure.

[0061] The processor 306 may include various processing circuitry and communicate with the memory 308, the I / O interface 302, the network communication manager 304, the database 310, the communication interface 312, and the plurality of modules / units 314 via the communication bus 316. Examples of the communication bus 316 may include, but are not limited to, a Peripheral Component Interconnect (PCI) / PCI Extended (PCI-X) bus, Small Computer System Interface (SCSI), Universal Serial Bus (USB), and a Front Side Bus (FSB). Aspects of the present disclosure are intended to include or otherwise cover any type of coupling means present or related to later developed technologies, that may be configured to connect the processor 306 to the other subsystems of the server 140 without deviating from the scope of the present disclosure.

[0062] The processor 306 is configured to execute a set of instructions stored in the memory 308 and to perform various processes. The processor 306 may also include a plurality of processing engines i.e., information processing units for controlling overall operation of the server 140. For an example, the processor 306 is configured to execute programs and processes to execute instruction(s) or code(s) stored in the memory 308 pertaining to prediction of the user traffic trends. The processor 306 is further configured to move data into or out of the memory 308 as required by an execution process of the server 140.

[0063] The processor 306 may include one or a plurality of processors, including a general-purpose processor, such as, for example, and without limitation, a Central Processing Unit (CPU), an Application Processor (AP), a dedicated processor, a graphics-only processing unit such as a Graphics Processing Unit (GPU), a programmable logic device, or any combination thereof.

[0064] The memory 308 stores the set of instructions required by the processor 306 of the server 140 for controlling its overall operations. The memory 308 may include non-volatile storage elements. Examples of such non-volatile storage elements may include magnetic hard discs, optical discs, floppy discs, flash memories, Read Only Memory (ROM) 308-1 or forms of electrically programmable memories (EPROM) or electrically erasable and programmable (EEPROM) memories. In addition, the memory 308 may, in some examples, be considered a non -transitory storage medium. The "non-transitory" storage medium is not embodied in a carrier wave or a propagated signal. However, the term "non-transitory" should not be interpreted as the memory 308 is non-movable. In some examples, the memory 308 may be configured to store larger amounts of information. In certain examples, a non- transitory storage medium may store data that can, over time, change (e.g., in Random Access Memory (RAM) 308-2 or cache). The memory 308 can be an internal storage unit or it can be an external storage unit of the server 140, cloud storage, or any other type of external storage. In some embodiments, when the memory 308 is external to the server 140, the memory 308 may be removably attached to the server 140. Aspects of the present disclosure are intended to include or otherwise cover any data storage medium as ‘the memory 308’, without deviating from the scope of the present disclosure.

[0065] The processor 306 is configured to utilize output data generated by a ML model 308-3 stored in the memory 308. The ML model 308-3 may include, but not limited to, an unsupervised, a semi-supervised, a supervised model or reinforcement learning model. In one embodiment, the ML model 308-3 may be pre-trained. The processor 306 is further configured for executing instructions stored in the memory 308. The memory 308 may store program instructions for performing several functions through which the user traffic trends may be predicted, and the visualization data may be generated.

[0066] In an embodiment, the module(s) 314 may be implemented as a combination of hardware and software programming (for example, programmable instructions) to implement one or more functionalities of the server 140. In non-limitingexamples, described herein, such combinations of hardware and software programming may be implemented in several different ways, without deviating from the scope of the present disclosure. The module(s) 314 may include suitable logic, circuitry, interfaces, and / or codes. For example, the programming for the module(s) 314 may be processor-executable instructions stored on a non-transitory machine-readable storage medium and the hardware for the module(s) 314 may comprise a processing resource (for example, one or more processors), to execute such instructions. In an embodiment, the module(s) 314 may be combined to a single module or each module of the module(s) 314 may be further subdivided into different modules.

[0067] In the present examples, the machine-readable storage medium may store instructions that, when executed by the processing resource, implement the module(s) 314. In such examples, the server 140 may also comprise the machine- readable storage medium storing the instructions and the processing resource to execute the instructions, or the machine-readable storage medium may be separate but accessible to the server 140 and the processing resource. In other examples, the module(s) 314 may be implemented using an electronic circuitry.

[0068] In one or more embodiments, the module(s) 314 may include one or more modules such as an acquisition module 314-2, a data computational module 314-4, a processing module 314-6, a transceiver module 314-8, and other modules (not shown in Fig. 3). The other modules may include a visualization generation module. Each of the module(s) 314 are communicatively coupled with each other.

[0069] In an embodiment, the processor 306, using the acquisition module 314-2, is configured to obtain, from one or more of the data collection entity 220, the serving cells 110, and the UEs 120, the network data for predicting a trend in a user traffic (same as the aforementioned “user traffic trend”) in the communication network 100. The network data includes the first set of KPIs associated with the plurality of UEs 120 and the second set of KPIs corresponds to the data associated with the serving cells 110 serving the plurality of UEs 120. The user traffic trendmay correspond to a pattern of growth, variation, and distribution of users over a consistent period of time across a geographical location.

[0070] Further, the processor 306, using the data computational module 314-4, is configured to utilize the data model 308-3, for predicting the trend in the user traffic served by a set of serving cells among the plurality of serving cells 110 during a predefined time-period based on the collected network data. The processor 306, using the data computational module 314-4, is configured to prepare a dataset from the network data for processing through the ML model 308-3. To prepare the dataset, the processor 306 fetches the network data stored from the storage medium 230 and synchronizes each information of the network data according in a plurality of time frames during the pre-defined time-period. The processor 306 stores the synchronized network data in the database 310.

[0071] In one embodiment, the processor 306, using the data computational module 314-4, may perform pre-processing of the synchronized network data stored in the database 310. The pre-processing operations may include data cleaning and data validation. Further, the processor 306, using the data computational module 314-4, is configured to aggregate from the processed network data, the first set of KPIs and the second set of KPIs at a plurality of timestamps of a rolling time window among a plurality of rolling time windows. The ruling time window corresponds to a technique that is used to process the aggregated network data over a fixed time duration that rolls forward as new aggregated network data arrives. The plurality of rolling time windows may be configured and / or pre-defined corresponding to different time intervals such as a 5-minute rolling time window, a 15-minute rolling time window or a 1 hour rolling time window. The pre-defined rolling time window is a technique used to compute metrics over a subset of data points that rolls sequentially through the dataset. The pre-defined rolling time window involves defining a fixed window size and calculating a statistical value such as a mean, sum, or standard deviation for the data points within that window..

[0072] The network operators using the data computational module 314-4, may predefine one or more pre-defined threshold ranges for each KPI in the first set of KPIs and each KPI in the second set of KPIs. The one or more pre-defined threshold ranges for each KPI may indicate a quality of the KPI, such as good, average, or poor. For an example, a first threshold range may indicate good performance metrics corresponding to each KPI, a second threshold range may indicate average performance metrics corresponding to each KPI, and a third threshold range may indicate poor performance metrics corresponding to each KPI. For an example, for an aggregated value of the SINK, a first threshold range indicating good performance metrics may be greater than 20 dB, a second threshold range indicating average performance metrics may be between 10 to 20 dB, and a third threshold range indicating poor performance metrics may be below 10 dB.

[0073] Further, the processor 306, using the data computational module 314-4, determines an average value of each KPI in each of the first set of KPIs and the second set of KPIs at each timestamp of the plurality of timestamps of the predefined rolling time window. The average value may correspond to a measure of central tendency such as a mean value, a median, a mode, a geometric mean, a harmonic mean, a weighted mean, a truncated mean, a midrange mean, and a trimean.

[0074] In one scenario, the first set of KPIs and the second set of KPIs may be aggregated for a 5-minute rolling time window. Below mentioned exemplary Table 1 depicts average values of KPIs such as RSRP and SINR measured in decibels (dB) among the first set of KPIs and average value of active user count among the second set of KPIs over a pre-defined time-period of 15 minutes from 10:00 am to 10: 15 am in a plurality of rolling time windows of 5 minutes.Table 1

[0075] As depicted in Table 1, a first rolling time window is from 10:00 am to 10:05 am where average values corresponding to the active user count is equal to 50, the RSRP is equal to -85 dB, and the SINR is equal to 25 dB are aggregated. In a second rolling time window from 10:05 am to 10: 10 am, next average values corresponding to the active user count equal to 120, the RSRP is equal to -98 dB, and the SINR is equal to 17 dB are aggregated. In a third rolling time window from 10: 10 am to 10: 15 am, subsequent average values to the active user count equal to 180, the RSRP is equal to -105 dB, and the SINR is equal to 9 dB are aggregated.

[0076] Furthermore, the processor 306, using the data computational module 314- 4, compares the average value of each KPI in each of the first set of KPIs and the second set of KPIs with one or more pre-defined threshold ranges of the first set of KPIs and the second set of KPIs. Corresponding to the values of KPIs in the first set of KPIs and the second set of KPIs as depicted in example scenario of above- mentioned Table 1, the processor 306, using the data computational module 314-4, compares the average value of SINR in each 5-minute rolling time window with the one or more pre-defined threshold ranges of the SINR. For example, the processor 306, using the data computational module 314-4, determines whether the average value of the SINR in the first rolling time window i.e. 25 dB is greater than 20 dB, lies between a range of 10 to 20 dB, or is below 10 dB. Similarly, the data computational module 314-4, determines whether the average value of the SINR in the second rolling time window i.e. 17 dB is greater than 20 dB, lies between a range of 10 to 20 dB, or is below 10 dB. The data computational module 314-4 further determines whether the average value of the SINR in the third rolling time window i.e. 9 dB is greater than 20 dB, lies between a range of 10 to 20 dB, or is below 10 dB. Similarly, the processor 306, using the data computational module 314-4, compares the average value of each KPI in the pre-defined rolling time window with the one or more pre-defined threshold ranges of the KPIs.

[0077] Based on a result of a comparison, the processor 306, using the data computational module 314-4, identifies a pre-defined threshold range of the one or more pre-defined threshold ranges that includes the average value of each KPI inthe pre-defined rolling time. The data computational module 314-4 utilizes semantic classification of KPIs values corresponding to the identified pre-defined threshold range to enrich the dataset with contextual labels. For an example, the average value of the KPI may be classified or labelled as good quality when it is identified to fall within the first pre-defined threshold range, the average value of the KPI may be classified or labelled as average quality when it is identified to fall within the second pre-defined threshold range, and the average value of the KPI may be classified or labelled as poor quality when it is identified to fall within the third pre-defined threshold range. The labelled dataset enables the ML model 308-3 to accurately process numerical values of the KPIs and also learn patterns of the user traffic trends based on quality categories of the KPIs.

[0078] In the aforementioned example scenario, the average value of the SINK in the first rolling time window is identified to be greater than 20 dB, the average value of the SINR in the second rolling time window identified to lie in the range of 10 dB to 20 dB, and the average value of the SINR in the third rolling time window is identified to lie below 10 dB. The processor 306, using the data computational module 314-4, classifies the average value of the SINR in the first rolling time window with the first threshold range of the SINR, the average value of the SINR in the second rolling time window with the second threshold range of the SINR, and the average value of the SINR in the third rolling time window with the third threshold range of the SINR. The labelling of the dataset creates a dual-layer feature set for the ML model 308-3 combining raw values of the KPIs with semantic performance classes, which improves interpretability and robustness of the ML model 308-3.

[0079] The database 310 may store the pre-processed network data, the processed network data, and the labelled dataset fed to the ML model 308-3. Furthermore, the database 310 is configured to store an output generated by the ML model 308-3 during different time periods corresponding to the serving cells 110 deployed in the geographical region. The database 310 is further configured to store large volumes of output data of the ML model 308-3 comprising predictions of user traffic trendscorresponding to a set of serving cells among the serving cells 110 during the predefined time-period. The database 310 also stores prioritization of one or more serving cells in the set of serving cells for adjusting one or more parameters of resource allocation based on the predicted user traffic trend. The database 310 may further store a current resource allocation to the set of serving cells and a change in resource allocation performed in the set of serving cells by the server 140.

[0080] The database 310 may be accessed and updated by the processor 306. The database 310 may be implemented as one or more of centralized database, Relational Database Management System (RDBMS), Non-Relational Database Management System, Hierarchical Database Management System, Network Database Management System, an in-memory database including a distributed inmemory data storage, distributed database, or a distributed file system.

[0081] The labelled dataset including the identified pre-defined threshold range is encoded into features that are fed into the ML model 308-3, in parallel with raw values of the KPIs in the dataset. The ML model 308-3 analyses the labelled dataset to predict the user traffic at the serving cells 110. The ML model 308-3 may comprise a machine learning component to perform a plurality of machine learning and deep learning operations on the on the dataset. In one embodiment, the ML model 308-3 may include one or more models based on linear regression, logistic regression, decision trees, random forest, Support Vector Machines (SVM), neural networks, K-Means clustering, hierarchical clustering, Density-Based Spatial Clustering of Applications with Noise (DBSCAN), Apriori Algorithm, and Principal Component Analysis (PCA). Further, the processor 306 may also be configured to fine-tune the ML model 308-3 as per requirement of network operators.

[0082] Based on the identified pre-defined threshold ranges in the labelled dataset, the data computational module 314-4 is configured to utilize the ML model 308-3 to capture moving averages and standard deviations in the rolling time windows. The data computational module 314-4 is configured to utilize the ML model 308-3 to determine a deviation in the average value of each KPI when the average valuefalls outside the pre-defined threshold range in a subsequent rolling time window of the plurality of pre-defined rolling time windows. For example, the ML model 308- 3 processes the labelled input dataset to determine whether the average value of the SINK in the first rolling time window falls outside the identified first threshold range of the SINK in subsequent rolling time windows i.e. the second rolling time window and the third rolling time window. Similarly, the ML model 308-3 processes the labelled input dataset to determine whether the average value of the SINK in the second rolling time window falls outside the identified second threshold range of the SINK in subsequent rolling time windows i.e. the third rolling time window, and whether the average value of the SINK in the third rolling time window falls outside the identified third threshold range of the SINK in a next pre-defined rolling time window. The data computational module 314-4 using the ML model 308-3 is configured to flag sudden shifts in of each KPI in the pre-defined threshold ranges, such as from good to poor. Identification of the sudden shifts or deviations enhance sensitivity of the ML model 308-3 to transient changes in the user traffic.

[0083] Further, the data computational module 314-4 using the ML model 308-3, identifies a historical pattern of the user traffic at each serving cell of the plurality of serving cells during the pre-defined rolling time window based on the determined deviation. To identify the historical user traffic trends, the average value of each KPI in the first set of KPIs and the second set of KPIs are not treated in isolation by the ML model 308-3. The ML model 308-3 uses feature correlation and temporal analysis to find patterns of interdependence between each KPI over time.

[0084] In an embodiment, the ML model 308-3 may perform dimensionality reduction on the labelled dataset to understand latent relationships in multivariate space of one or more KPI of the first set of KPIs and the second set of KPIs. The ML model 308-3 may utilize statistical correlation to find one or more linear or nonlinear relationships between the one or more KPIs among the first set of KPIs, the one or more KPIs among the second set of KPIs, and the one or more KPIs in the first set of KPIs and the second set of KPIs. For an example, an increase in average value of the active user count may often lead a decrease in average value of theSINR. Thus, the ML model 308-3 is configured to use causal discovery algorithms to determine which KPIs cause changes in others.

[0085] Further, the ML model 308-3 may perform lag correlation between the one or more KPIs among the first set of KPIs, the one or more KPIs among the second set of KPIs, and the one or more KPIs in the first set of KPIs and the second set of KPIs, to identify time-shifted relationships. For an example, a spike in the average value of the RSRP drop may precede a degradation in the average value of the SINR. Further, the ML model 308-3 may perform feature engineering to capture dynamic relationships between the one or more KPIs among the first set of KPIs, the one or more KPIs among the second set of KPIs, and the one or more KPIs in the first set of KPIs and the second set of KPIs and derive interdependent metrics, for an example a ratio of “RSRP-to-active user count” or “a change in SINR to spike in active user count”.

[0086] Furthermore, the data computational module 314-4 using the ML model 308-3, based on the identified historical pattern of the user traffic, predicts the trend in the user traffic of the set of serving cells among the plurality of serving cells during the pre-defined rolling time window. For predicting the user traffic trend, the ML model 308-3 dynamically learns multivariate KPI trajectories that precede quality degradation, rather than relying on static breach of the one or more pre-defined threshold ranges.

[0087] In another embodiment, for predicting the trend, the data computational module 314-4 using the ML model 308-3, determines from the collected network data, a traffic behavior profile of a UE of the plurality of UEs 120 based on one or more a type of service availed by the UE from the communication network, a time of availing the service, a device type of the UE that has availed the service.

[0088] The behavior profile of the UE may correspond to a traffic profile of the UE based on a device type or device configuration of the UE and usage of the UE for availing different type of services including, but not limited to, video streaming, operating Internet of Things (loT) devices, and gaming. The ML model 308-3 learnsuser traffic trend patterns per behavior profile. The behavior profiles are captured over time and the ML model 308-3 predicts the user traffic trend based on the behavior profile instead of only relying on breaches in one or more pre-defined threshold ranges of the KPIs. For learning the patterns of the behavior profile, an unsupervised ML model 308-3 may be utilized. In another embodiment, the ML- model 308-3 may be re-trained based on a feedback loop of the predicted trend and the behavior profile.

[0089] Upon predicting the trend in the user traffic, the processor 306, using the data computation module 314-4, is configured to identify one or more serving cells in the set of serving cells for adjusting parameters corresponding to one or more resources of the one or more serving cells. Based on the predicted the trend in the user traffic and the identified one or more serving cells, the processor 306, using the processing module 314-6 is configured to generate visualization data including information related to the one or more resources of the one or more serving cells during the pre-defined time-period.

[0090] The generated visualization data may include a current resource allocation of the identified one or more serving cells, the predicted user traffic trend in the identified one or more serving cells, and other information corresponding to the identified one or more serving cells. In one embodiment, from the generated visualization data, the processing module 314-6 may determine the priority of the identified one or more serving cells for managing the resource allocation corresponding to the predicted user trend, in a decreasing or increasing order of priority. For example, a high priority may be set for the one or more serving cells in the set of serving cells 110 predicted to experience high user traffic. In another embodiment, the generated visualization data may comprise a performance metric report including information indicative of performance of the set of serving cells serving the plurality of UEs 120.

[0091] In one embodiment, the processor 306 using the processing module 314-6, is configured to adjust the parameters corresponding to the one or more resourcesbased on an analysis obtained from the generated visualization data, the parameters may include, but not limited to, bandwidth allocation, antennae directions, tilt, azimuth, and antennae angles. The one or more resources correspond to one or more of the serving cells 110 serving the UEs 120, neighboring serving cells of the serving cells 110 serving the UEs 120, network devices, and computing resources in the communication network. For adjusting the one or more parameters, the processing module 314-6 may set up scheduling algorithm for adjusting the one or more parameters, performing adjustment of network capacity, and traffic routing, changing existing Quality of Service (QoS) policies or implement new QoS policies, perform carrier aggregation, and altering beamforming such as controlling the phase and amplitude of signals sent to each antenna in the array, creating a narrow, focused beam, corresponding to the one or more resources.

[0092] The processor 306 is configured to dynamically adjust the predicted trend in the user traffic based on volatility in a current environment of the communication network, a change in type of services availed by the UE, and a confidence parameter of the predicted trend based on a feedback sent to the ML-model 308-3.

[0093] The network communication manager 304, using the transceiver module 314-8, is configured to send the generated visualization data to the NMC 210 for displaying the generated visualization data on the GUI 212, for the adjustment of the parameters corresponding to the one or more resources. The transceiver module 314-8 may receive incoming RF signals, such as signals transmitted by the nodes 110 and the UEs 120 in the communication network. The transceiver module 410-1 may down-convert the incoming RF signals to generate the IF or baseband signals which may be sent to the receiver processing circuitry. The transceiver module 410- 1 may transmit the processed baseband signals to the processor 306 for further processing. The transceiver module 314-8 may receive analog or digital data from the processor 306 and may encode, multiplex, and / or digitize the outgoing baseband data to generate processed baseband or IF signals. The transceiver module 314-8 may further process the outgoing processed baseband or IF signals from the transmitprocessing circuitry and up-converts the baseband or IF signals to RF signals that may be transmitted to the nodes 110, the UEs 120, and the NMC 210.

[0094] The network communication manager 304 is configured to render the visualization data on the GUI 212 of the NMC 210. The network communication manager 304 helps in displaying the visualization of the prioritization of the identified serving cells and the predicted user traffic trends related to the identified serving cells during the pre-defined time-period in an engaging and interactive format on the GUI 212. The network communication manager 304 helps in rendering the visualization data in one or more pictorial format, graphical format, tabular format, and report format. Further, the network communication manager 304 manages creation and manipulation of graphical elements such as charts, diagrams, or highlighted text that enhance the comprehension and presentation of the visualization data. By optimizing the graphical output, the network communication manager 304 304 ensures dynamic visualization of the current resource allocation and the predicted user traffic on the set of serving cells, thereby improving the resource allocation management in the communication network 100.

[0095] In one embodiment, based on the generated visualization data, the network operator may manually adjust the parameters corresponding to the one or more resources based on an analysis obtained from the generated visualization data.

[0096] The communication interface 312 may manage communications with the NMC 210, the network 130, the data collection entity 220, and the database 230. For example, the communication interface 312 may manage the reception of the network data from the data collection entity 220. The communication interface 312 may include an electronic circuit specific to a standard that enables wired or wireless communication. The communication interface 312 is configured for communicating with external devices via one or more networks.

[0097] Although FIG. 3 illustrates one example of server 140, various changes may be made to FIG. 3. For example, the server 140 may include any number of components in addition to the components shown in FIG. 3. Further, variouscomponents in FIG. 3 may be combined, further subdivided, or omitted and additional components may be added according to particular needs. A detailed description of the method for predicting user traffic trends for resource allocation management in the communication networks is described further below.

[0098] FIG. 4 illustrates a flow chart of a method 400 for predicting user traffic trends for resource allocation management in the communication networks, in accordance with an embodiment of the present disclosure. The method 400 comprises a series of operations steps indicated by blocks 402 through 412 performed by the processor 306 embedded in the server 140. The method 400 begins at block 402.

[0099] At block 402, the processor 306, using the acquisition module 314-2, collects the network data from the plurality of serving cells serving the UEs 120. The acquisition module 314-2 may collect the network data via the data collection entity 220 at a pre-defined frequency and prepare the dataset from the received network data. The network data may include information related to at least one of the number of active UEs, the total number of UEs, historical network usage data associated with the UE, the type of service availed by the UE from the communication network 100, the time of availing the service, the type of the UE availing the services, and one or more of the first set of KPIs related to the plurality of UEs 120 and the second set of KPIs related to the plurality of serving cells 110. The network data may further include historical network usage data by the subscribers during the time-period, subscriber behavior data, and information corresponding to geographical location of the serving cells 110 and the UEs 120. Furthermore, the network data may include real-time data such as network performance metrics and subscriber activity corresponding to the serving cells 110.

[0100] The processor 306 performs pre-processing operations over the received data. The pre-processing operations may include operations such as, but not limited to, network data cleaning and network data validation according to data stored in the server 140.

[0101] Further, at step 404, the processor 306, using the data computation module 314-4, prepares the dataset from the synchronized network data stored in the database 310 for further analysis using the ML model 308-3 for prediction of the trend. To prepare the dataset, the processor 306, using the data computation module 314-4, determines the average value of each KPI in each of the first set of KPIs and the second set of KPIs at each timestamp of the plurality of timestamps of the predefined rolling time windows. The processor 306, using the data computation module 314-4, compares the average value of each KPI in each of the first set of KPIs and the second set of KPIs with one or more pre-defined threshold ranges of the first set of KPIs and the second set of KPIs. Based on a result of the comparison, processor 306, using the data computation module 314-4, identifies a pre-defined threshold range among the one or more pre-defined threshold ranges that includes the average value of each KPI in the pre-defined rolling time window.

[0102] At step 406, the input dataset is provided to the ML model 308-3 for further analysis. The ML model 308-3 applies machine learning techniques over the input dataset for predicting the trend of the user traffic observed over the pre-defined time-period such as dates, days, months, or other pre-defined time periods of a year. For predicting the trend, the data computation module 314-4 using the ML model 308-3, determines, based on the identified pre-defined threshold range, a deviation in the average value of each KPI when the average value falls outside the identified pre-defined threshold range in a subsequent rolling time window of the plurality of pre-defined rolling time windows. The data computation module 314-4 using the ML model 308-3, identifies the historical pattern of the user traffic at each serving cell of the plurality of serving cells 110 during the pre-defined rolling time window based on the determined deviation. In another embodiment, the data computation module 314-4 using the ML model 308-3, identifies the traffic behavior profile of the UE of the plurality of UEs 120 based on one or more a type of service availed by the UE from the communication network 100, the time of availing the service, the device type of the UE that has availed the service.

[0103] At step 408, based on one or more of the identified historical pattern of the user traffic and the traffic behavior profile of the UE, the data computation module using the ML model 308-3, predicts the trend in the user traffic served by a set of serving cells among the plurality of serving cells 110 during the pre-defined time-period at a specified future date, day, month, or other pre-defined time frame of a year. The prediction of the user traffic may be refined by the ML model 308-3 based on a current volatility in the communication network 100 and changes in the traffic behavior profile.

[0104] At step 408, based on the output of the ML model 308-3, based on the predicted trend in the user traffic, the data computation module 314-4, identifies the one or more serving cells in the set of serving cells for adjusting the parameters corresponding to one or more resources of the one or more serving cells.

[0105] At step 410, the output of the ML model 308-3 is processed by the processing module 314-6, for generating based on the predicted trend in the user traffic and the identified one or more serving cells, visualization data including information related to the one or more resources of the one or more serving cells during the pre-defined time-period, and information related to the predicted user traffic trend of the set of serving cells based on the prioritization. In one embodiment, from the generated visualization data, the processing module 314-6 may determine the priority of the identified one or more serving cells for managing the resource allocation corresponding to the predicted user trend, in a decreasing or increasing order of priority The visualization data may be sent for display to the network operator in a graphical format or pictorial format over the NMC 210.

[0106] In one embodiment, the visualization data may be used to generate the performance metric report based on the predicted user traffic. The performance metric report includes an indicative performance of the set of serving cells to serve the plurality of UEs and a user traffic comparison between serving cells 110 at various geographical locations at the pre-defined time-period. The performance metric report may include, but not limited to, graphical or tabular representations ofgeographical locations or the serving cells experiencing high user traffic, medium user traffic, and low user traffic.

[0107] At step 412, the processor 306 using the processing module 314-6, is configured to adjust the parameters corresponding to the one or more resources based on the generated visualization data. In one embodiment, based on an assessment of the generated visualization data, the prioritization and the performance metric report, the network operators may adjust and / or manage resource allocation pre-emptively for optimization of user experience in the communication network 100. The network operators may adjust and / or manage the resource allocation or take required action pre-emptively for improving performance of serving cells 110.

[0108] Although method 400 shows example blocks of steps 402 to 412, in some embodiments, the method 400 may include additional steps, fewer steps or steps in different order than those depicted in Fig. 4. In other embodiments, the steps 402 through 412 may be combined or may be performed in parallel.

[0109] In another embodiment, a portion of the dataset may be used to test the ML model 308-3. Accuracy and effectiveness of the prediction operation performed using the ML model 308-3 may be tested using the historical data. In yet another embodiment, by changing the dataset, the system 200 may be used to simulate scenarios of high user traffic for resource management and test the efficiency of the ML model 308-3.

[0110] Now, referring to the technical abilities and advantageous effect of the present disclosure, operational advantages that may be provided by one or more embodiments may include providing a unique and efficient system that helps in predicting user traffic trends, and preemptively adjust parameters for resource allocation in the communication network. The disclosed system and the method further provide an integration of predictive analytics with real-time resource management in the communication network through utilization of the ML model. As a result, the present disclosure helps in assisting the network operators to adopta pro-active approach for enhancement of network performance to improve user experience and optimize resource utilization in the communication network. The present disclosure further allows the network operators to scale network infrastructure by anticipating future user traffic trends.

[0111] Further, the present disclosure aids the network operators to optimize their infrastructure investments by ensuring that existing resources are allocated efficiently, minimization of wasted capacity of the resources during low-demand periods in the communication network and scaling up the resources as per need during peak user traffic. The present disclosure helps to improve cost efficiency of the communication network by reducing unnecessary capacity provisioning in the communication network and improving utilization of existing network resources.

[0112] Another noteworthy advantage offered by the present disclosure is that through the use of the labelled dataset including classification of the KPIs with the one or more pre-defined threshold ranges results in an accurate prediction of the trend, thereby preventing overreaction of the system to noise or underreaction to real patterns. Furthermore, the present disclosure offers an effective system and method for prediction of the trend as it identifies causal Inference Between each KPI from and among the first set of KPIs and the second set of KPIs. Yet another advantage offered by the present disclosure is that the ML model is configured to adjust the prediction of the trend based on the volatility in the communication network, sensitivity to the type of service availed, and dynamically decide on how far to look ahead for deviation in the average values of the KPIs in real time.

[0113] Embodiments of the present technology may be described herein with reference to flowchart illustrations of methods and systems according to embodiments of the technology, and / or procedures, algorithms, steps, operations, formulae, or other computational depictions, which may also be implemented as computer program products. In this regard, each block or step of the flowchart, and combinations of blocks (and / or steps) in the flowchart, as well as any procedure, algorithm, step, operation, formula, or computational depiction can be implementedby various means, such as hardware, firmware, and / or software including one or more computer program instructions embodied in computer-readable program code. As will be appreciated, any such computer program instructions may be executed by one or more computer processors, including without limitation a general -purpose computer or special purpose computer, or other programmable processing apparatus to perform a group of operations comprising the operations or blocks described in connection with the disclosed methods.

[0114] Further, these computer program instructions, such as embodied in computer-readable program code, may also be stored in one or more computer- readable memory or memory devices (for example, the memory 308) that can direct a computer processor or other programmable processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory or memory devices produce an article of manufacture including instruction means which implement the function specified in the block(s) of the flowchart(s).

[0115] It will further be appreciated that the term “computer program instructions” as used herein refer to one or more instructions that can be executed by the one or more processors (for example, the processor 306) to perform one or more functions as described herein. The instructions may also be stored remotely such as on a server, or all or a portion of the instructions can be stored locally and remotely.

[0116] Those skilled in the art will appreciate that the methodology described herein in the present disclosure may be carried out in other specific ways than those set forth herein in the above disclosed embodiments without departing from essential characteristics and features of the present invention. The abovedescribed embodiments are therefore to be construed in all aspects as illustrative and not restrictive.

[0117] The drawings and the forgoing description give examples of embodiments. Those skilled in the art will appreciate that one or more of the described elements may well be combined into a single functional element.Alternatively, certain elements may be split into multiple functional elements. Elements from one embodiment may be added to another embodiment. For example, orders of processes described herein may be changed and are not limited to the manner described herein. Any combination of the above features and functionalities may be used in accordance with one or more embodiments.

[0118] In the present disclosure, each of the embodiments has been described with reference to numerous specific details which may vary from embodiment to embodiment. The foregoing description of the specific embodiments disclosed herein may reveal the general nature of the embodiments herein that others may, by applying current knowledge, readily modify and / or adapt for various applications such specific embodiments without departing from the generic concept, and, therefore, such adaptations and modifications are intended to be comprehended within the meaning of the disclosed embodiments. It is to be understood that the phraseology or terminology employed herein is for the purpose of description and is not limited in scope.LIST OF REFERENCE NUMERALS

[0119] The following list is provided for convenience and in support of the drawing figures and as part of the text of the specification, which describe innovations by reference to multiple items. Items not listed here may nonetheless be part of a given embodiment. For better legibility of the text, a given reference number is recited near some, but not all, recitations of the referenced item in the text. The same reference number may be used with reference to different examples or different instances of a given item. The list of reference numerals is:100 - Exemplary environment of a wireless communication network110 - Plurality of nodes120 - Plurality of User Equipment (UE)130 - Network140 - Server200 - System for predicting user traffic trends for resource allocation management in a communication network210 - Network Management Console (NMC)212 - Graphical User Interface (GUI)214 - Communication unit220 - Data Collection Entity230 - Storage medium302 - Input / Output (I / O) Interface304 - Network Communication Manager306 - Processor(s)308 - Memory308-1 - Read Only Memory (ROM)308-2 - Random Access Memory (RAM)308-3 - Computational Model310 - Database312 - Communication Interface314 - Module(s) / Unit(s)314-2 - Acquisition Module314-4 - Data Computation Module314-4 - Processing Module314-8 - Transceiver Module316- Communication Bus400- Method for predicting user traffic trends for resource allocation management in the communication network402-412 - Operation steps of the method 400

Claims

WE CLAIM:

1. A method (400) for predicting user traffic trends for resource allocation management in a communication network (100), the method (400) comprising: collecting, by an acquisition module (314-2), network data from a plurality of serving cells (110) serving a plurality of User Equipment (UEs) (120) in the communication network (100); predicting, by a data computation module (314-4) using a computational model (308-3), a trend in a user traffic served by a set of serving cells among the plurality of serving cells (110) during a pre-defined time-period based on the collected network data; identifying, by the data computation module based on the predicted trend in the user traffic, one or more serving cells in the set of serving cells for adjusting parameters corresponding to one or more resources of the one or more serving cells; generating, by a processing module (314-6) based on the predicted trend in the user traffic and the identified one or more serving cells, visualization data including information related to the one or more resources of the one or more serving cells during the pre-defined time-period; and adjusting, by the processing module (314-6), the parameters corresponding to the one or more resources based on the generated visualization data.

2. The method (400) as claimed in claim 1, for predicting the trend, the method (400) further comprises: aggregating, by the data computation module (314-4) from the network data, a first set of Key Performance Indicators (KPIs) related to the plurality of UEs (120) and a second set of KPIs related to the plurality of serving cells (110) at a plurality of timestamps of a pre-defined rolling time window among a plurality of pre-defined rolling time windows; determining, by the data computation module (314-4), an average value of each KPI in each of the first set of KPIs and the second set of KPIsat each timestamp of the plurality of timestamps of the pre-defined rolling time window; comparing, by the data computation module (314-4), the determined average value with one or more pre-defined threshold ranges of the first set of KPIs and the second set of KPIs; and identifying, by the data computation module (314-4) based on the comparison, a pre-defined threshold range among the one or more predefined threshold ranges that includes the determined average value of each KPI.

3. The method (400) as claimed in claim 2, for predicting the trend, the method (400) further comprises: determining, by the data computation module (314-4) using the computational model (308-3) based on the identified pre-defined threshold range, a deviation in the average value of each KPI when the average value falls outside the identified pre-defined threshold range in a subsequent rolling time window of the plurality of pre-defined rolling time windows; identifying, by the data computation module (314-4) using the computational model (308-3), a historical pattern of the user traffic at each serving cell of the plurality of serving cells (110) during the pre-defined rolling time window based on the determined deviation; and predicting, by the data computation module (314-4) using the computational model (308-3), the trend in the user traffic of the set of serving cells among the plurality of serving cells (110) during the pre-defined rolling time window based on the identified historical pattern of the user traffic.

4. The method (400) as claimed in claim 1, wherein for predicting the trend, the method further comprises, determining, by the data computation module (314-4) using the collected network data, a traffic behavior profile of a UE of the plurality of UEs (120) based on one or more a type of service availed by the UE from the communication network (100), a time of availing the service, a device type of the UE that has availed the service.

5. The method (400) as claimed in claim 1, wherein the network data includes information related to at least one of a number of active UEs among the plurality of UEs (120) served by a serving cell of the plurality of serving cells (110) during the pre-defined time-period, a total number of UEs among the plurality of UEs (120) attached to the serving cell during the pre-defined time-period, historical network usage data associated with a UE of the plurality of UEs (120) during the pre-defined time-period, a type of service availed by the UE from the communication network (100), a time of availing the service, a type of the UE availing the services, and one or more of a first set of Key Performance Indicators (KPIs) related to the plurality of UEs (120) and a second set of KPIs related to the plurality of serving cells (110).

6. The method (400) as claimed in claim 1, comprising: sending, by a transceiver module (314-8), the generated visualization data to a network management device (210) for displaying the generated visualization data for the adjustment of the parameters corresponding to the one or more resources, wherein the generated visualization data comprises a performance metric report including information indicative of performance of the set of serving cells serving the plurality of UEs (120).

7. A system (200) for predicting user traffic trends for resource allocation management in a communication network (100), the system (200) comprising: an acquisition module (314-2) configured to collect network data from a plurality of serving cells serving a plurality of User Equipment (UEs) (120) in the communication network (100); a data computation module (314-4) configured to: predict, using a computational model (308-3), a trend in a user traffic served by a set of serving cells among the plurality of serving cells (110) during a pre-defined time-period based on the collected network data; andidentify, based on the predicted trend in the user traffic, one or more serving cells in the set of serving cells for adjusting parameters corresponding to one or more resources of the one or more serving cells; and a processing module (314-6) configured to: generate, based on the predicted trend in the user traffic and the identified one or more serving cells, visualization data including information related to the one or more resources of the one or more serving cells during the pre-defined time-period; and adjust the parameters corresponding to the one or more resources based on the generated visualization data.

8. The system (200) as claimed in claim 7, wherein the data computation module (314-4) is further configured to: aggregate, from the network data, a first set of Key Performance Indicators (KPIs) related to the plurality of UEs (120) and a second set of KPIs related to the plurality of serving cells (110) at a plurality of timestamps of a pre-defined rolling time window among a plurality of pre-defined rolling time windows; determine an average value of each KPI in each of the first set of KPIs and the second set of KPIs at each timestamp of the plurality of timestamps of the pre-defined rolling time window; compare the determined average value of each KPI with one or more pre-defined threshold ranges of the first set of KPIs and the second set of KPIs; and identify, based on the comparison, a pre-defined threshold range among the one or more pre-defined threshold ranges that includes the determined average value of each KPI.

9. The system (200) as claimed in claim 8, wherein for predicting the trend, the data computation module (314-4) is configured to:determine, using the computational model (308-3) based on the identified pre-defined threshold range, a deviation in the average value of each KPI when the average value falls outside the identified pre-defined threshold range in a subsequent rolling time window of the plurality of predefined rolling time windows; identify, using the computational model (308-3), a historical pattern of the user traffic at each serving cell of the plurality of serving cells (110) during the pre-defined rolling time window based on the determined deviation; and predict, using the computational model (308-3), the trend in the user traffic of the set of serving cells among the plurality of serving cells (110) during the pre-defined rolling time window based on the identified historical pattern of the user traffic.

10. The system (200) as claimed in claim 7, wherein for predicting the trend, the data computation module (314-4) is further configured to determine, using the collected network data, a traffic behavior profile of a UE of the plurality of UEs (120) based on one or more a type of service availed by the UE from the communication network (100), a time of availing the service, a device type of the UE that has availed the service.

11. The system (200) as claimed in claim 7, wherein the network data includes information related to at least one of a number of active UEs among the plurality of UEs (120) served by a serving cell of the plurality of serving cells (110) during the pre-defined time-period, a total number of UEs among the plurality of UEs (120) attached to the serving cell during the pre-defined time-period, historical network usage data associated with a UE of the plurality of UEs (120) during the pre-defined time-period, a type of service availed by the UE from the communication network (100), a time of availing the service, a type of the UE availing the services, and one or more of a first set of Key Performance Indicators (KPIs) related to the plurality of UEs (120) and a second set of KPIs related to the plurality of serving cells (110).

12. The system (200) as claimed in claim 7, further comprising a transceiver module (314-8) configured to: send the generated visualization data to a network management device for displaying the generated visualization data for the adjustment of the parameters corresponding to the one or more resources, wherein the generated visualization data comprises a performance metric report including information indicative of performance of the set of serving cells serving the plurality of UEs (120).

13. A computer program product for predicting user traffic trends for resource allocation management in a communication network (100), the computer program product comprising computer-executable instructions that are stored on a non-transitory computer-readable medium and that, when executed by at least one processor performs operations comprising: collecting network data from a plurality of serving cells serving a plurality of User Equipment (UEs) in the communication network; predicting, using a computational model, a trend in a user traffic served by a set of serving cells among the plurality of serving cells during a pre-defined time-period based on the collected network data; identifying, based on the predicted trend in the user traffic, one or more serving cells in the set of serving cells for adjusting parameters corresponding to one or more resources of the one or more serving cells; generating, based on the predicted trend in the user traffic and the identified one or more serving cells, visualization data including information related to the one or more resources of the one or more serving cells during the pre-defined time-period; and adjusting the parameters corresponding to the one or more resources based on the generated visualization data.

Images